LaunchAI ModelsSeptember 23, 2026

Google DeepMind demos Gemini 3.8 text-to-speech voice creation

Read original source →youtube.com

Gemini 3.8 text-to-speech lets users design new vocal personas from scratch via natural-language prompts, directing performances line by line with acting cues, pacing, back channeling, and dialect shifts. It also recreates consistent adult vocal profiles.

1 source

More stories today

Open the live feed